BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160559Z
LOCATION:Track 11
DTSTART;TZID=America/New_York:20201113T124000
DTEND;TZID=America/New_York:20201113T130500
UID:submissions.supercomputing.org_SC20_sess229_ws_ai4s105@linklings.com
SUMMARY:How Good Is Your Scientific Data Generative Model?
DESCRIPTION:Workshop\n\nHow Good Is Your Scientific Data Generative Model?
 \n\nYang, Gremillion, Zhang, Lin, Wohlberg\n\nNowadays, leveraging data au
 gmentation methods on helping resolving scientific problems becomes prevai
 ling. And many scientific problems benefit from data augmentation methods 
 build with deep generative models. Yet due to the complexity of the scient
 ific data, commonly used evaluation methods of generative models appear no
 t so suitable for generated scientific data. In this paper, we explore how
  do we effectively evaluate data augmentation methods for scientific data 
 generative models? To answer this question, we use one example of real wor
 ld scientific problem to show how we evaluate the quality of the generated
  data from two domain specific deep generative models. We observe that mos
 t existing state-of-art evaluation metrics are incompetent. They either sh
 ow completely contradicting results or provide inaccurate insight from rea
 l data.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR